Prediction of nanoparticle transport behavior from physicochemical properties: Machine learning provides insights to guide the next generation of transport models

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Authors

In the last 15 years, the development of advection-dispersion particle transport models (PTMs) for the transport of nanoparticles in porous media has focused on improving the fit of model results to experimental data by inclusion of empirical parameters. However, the use of these PTMs has done little to elucidate the complex behavior of nanoparticles in porous media and has failed to provide the mechanistic insights necessary to predictively model nanoparticle transport. The most prominent weakness of current PTMs stems from their inability to consider the influence of physicochemical conditions of the experiments on the transport of nanoparticles in porous media. Qualitative physicochemical influences on particle transport have been well studied and, in some cases, provide plausible explanations for some aspects of nanoparticle transport behavior. However, quantitative models that consider these influences have not yet been developed. With the current work, we intend to support the development of future mechanistic models by relating the physicochemical conditions of the experiments to the experimental outcome using ensemble machine learning (random forest) regression and classification. Regression results demonstrate that the fraction of nanoparticle mass retained over the column length (retained fraction, RF; a measure of nanoparticle transport) can be predicted with an expected mean squared error between 0.025-0.033. Additionally, we find that RF prediction was insensitive to nanomaterial type and that features such as concentration of natural organic matter, ζ potential of nanoparticles and collectors and the ionic strength and pH of the dispersion are strongly associated with the prediction of RF and should be targets for incorporation into mechanistic models. Classification results demonstrate that the shape of the retention profile (RP), such as hyperexponential or linearly decreasing, can be predicted with an expected F1-score between 60-70%. This relatively low performance in the prediction of the RP shape is most likely caused by the limited data on retention profile shapes that are currently available.

OriginalspracheEnglisch
ZeitschriftEnvironmental Sciences: Nano
Jahrgang2
Ausgabenummer4
Seiten (von - bis)352-360
Anzahl der Seiten9
ISSN2051-8153
DOIs
PublikationsstatusErschienen - 2015

DOI

Zuletzt angesehen

Publikationen

  1. Eternal Life
  2. Falling “fortresses”
  3. Finanzmarktorientiertes Umweltmanagement
  4. Predictors of Principals' Engagement in School Health Promotion
  5. Error Orientation Questionnaire (EOQ)
  6. Does cognitive behaviour therapy have an enduring effect that is superior to keeping patients on continuation pharmacotherapy?
  7. Investigation of geometrical features on mechanical properties of AA2198 refill friction stir spot welds
  8. Historical emissions of octachlorodibenzodioxin in a watershed in Queensland, Australia
  9. Common Commercial Policy and External Trade
  10. Effects of Gd solutes on hardness and yield strength of Mg alloys
  11. Demokratie und Differenz - Ein Beispiel, Demokratie zu gestalten
  12. RE/viewing Jerusalem
  13. Ideologie
  14. Gewerblicher Grundstückshandel (Kommentierung des BFH-Urteils vom 05.12.2002, IV R 57/01), Fach 3 EStG, § 15
  15. Musik in transkulturellen Kontexten
  16. The Relationship Between the Environmental and Economic Performance of Firms
  17. Abschied von gestern
  18. The digital disruption of strategic paths
  19. PharmCycle
  20. Beschleunigung als soziales Problem
  21. Empirical Identification of Corporate Environmental Strategies
  22. Sprechsport
  23. Islamophobia without Muslims? The "contact Hypothesis" as an Explanation for Anti-Muslim Attitudes - Eastern European Societies in a Comparative Perspective
  24. Naturschutzrecht
  25. Qualitätssicherung der Tätigkeit des unabhängigen Finanzexperten
  26. Ziele der Partizipation von Kindern und Jugendlichen
  27. Im Epochenlosen
  28. Self-organized learning in vocational education
  29. A never ending story - Entwicklungen in der Frauenhausarbeit
  30. Pantomimisches Lernen in der Grundschule
  31. Normative Begründung der Nachhaltigkeitsökonomie
  32. Parlamentarismus
  33. Thermal cycling and creep studies of AM50+Nd magnesium alloy based carbon fiber, SiC particulate and IN-SITU Mg2Si reinforced hybrid composites
  34. Gelingensbedingungen für die Entwicklung guter gesunder Schulen
  35. Wie teuer ist (uns) die Umwelt?
  36. Die ausgelieferte Opposition
  37. Die zwei Körper des Textes
  38. Psychological approaches to entrepreneurial success
  39. THE ECONOMICS OF EARNINGS - POLACHEK,SW, SIEBERT,WS
  40. § 257 HGB
  41. Abschied vom Konsumschutzrecht
  42. Sisyphos oder Der Kampf um die Familie